Article

MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction

2026-04-29

Abstract excerpt

<title>Abstract</title> <p>Accurate clinical diagnosis requires extensive domain knowledge and complex clinical reasoning capabilities. Although large language models (LLMs) hold great potential for clinical reasoning, their high computational and memory requirements limit their deployment in resource-constrained environments. Knowledge distillation (KD) can compress LLM capabilities into smaller models, but trad...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 7e9ab2e9-00f1-5bfd-bf6d-2919a8ac7e80
DOI: 10.21203/rs.3.rs-9553270/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning CorrectionDOI 10.21203/rs.3.rs-9553270/v1Read

Evaluating a Large Reasoning Model’s Performance on Open-Ended Medical ScenariosSemantic proximity Read

The Economics of Accuracy for Medical Reasoning with Large Language ModelsSemantic proximity Read

RAGnosis: Retrieval-Augmented Generation for Enhanced Medical Decision MakingSemantic proximity Read

CARDBiomedBench: A Benchmark for Evaluating Large Language Model Performance in Biomedical ResearchSemantic proximity Read

Understanding Clinical Reasoning Variability in Medical Large Language Models: A Mechanistic Interpretability StudySemantic proximity Read

High Consistency, Limited Accuracy: Evaluating Large Language Models for Binary Medical DiagnosisSemantic proximity Read

Reasoning Over Pre-training: Evaluating LLM Performance and Augmentation in Women’s HealthSemantic proximity Read

Interpretable Fine-tuned Large Language Models Facilitate Making Genetic Test Decisions for Rare DiseasesSemantic proximity Read

Synthetic Data Distillation Enables the Extraction of Clinical Information at ScaleSemantic proximity Read

General purpose large language models match human performance on gastroenterology board exam self-assessmentsSemantic proximity Read

MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questionsSemantic proximity Read

Assessing the Performance of Plugin-Integrated ChatGPT-4 in the German Medical Board Examination: An Experimental Study on the Advancements and Limitations of Modern AI Modelling ApproachesSemantic proximity Read